Does the health data even exist for the problem you are trying to solve?

Launching our first FHIR Implementation Guide

Launching projects as a dev in health can be confusing. Health data has lots of competing definitions and standards and a rich history. The realities of health data make building as a startup challenging to say the least. One of the biggest is quite simply: “does the data even exist for the problem you are trying to solve?”

As we’ve written before, we encountered this very challenge when it came to trying to automate the interpretation of pulmonary function tests.

Today, Automate Medical is proud to launch our first FHIR Implementation Guide for pulmonary function data. As we’ve been saying internally, this is the end result of “going the distance” on introducing computability to an area of medicine that has been underserved by interoperability advances.

Medical source data is often not easily available in a digital format. Paper records, reports, test results and labs were “digitized” in the past, often only as PDFs in archive, making it hard to use this data to actually build your digital health solution. This is all especially true in the case of pulmonary function tests (PFTs).

Using our expertise from digitizing PFTs, we developed a brand new FHIR Implementation Guide for PFTs using MITRE’s FSH (pronounced 🐟) and SUSHI projects to define pulmonary function data in a FHIR system. We built this IG exclusively in-house, with internal dev support and advice from our clinical advisors.

Our Implementation Guide (IG) describes how to structure pulmonary function test data in an interoperable format. The IG currently profiles a DiagnosticReport with a minimal set of the most clinically significant discrete observations obtained from Spirometry or Diffusion Capacity. It is intentionally designed to provide guidance in conformance with reporting standardization efforts such as Recommendations for a Standardized Pulmonary Function Report by Culver et al.

The PFT, to-date, has not benefited from the advancement of interoperability standards. Today, we're hoping to change that.

As the working group in McCormack et al wrote in Electronic Health Records and Pulmonary Function Data: Developing an Interoperability Roadmap. An Official American Thoracic Society Workshop Report:

The ability to access PFT data within and between healthcare systems holds great promise for improving our understanding of lung diseases and the respiratory health of patients and the population. This would not only allow monitoring of trends in forced expiratory volume in 1 second in the same way one can typically monitor trends in other clinical laboratory values (e.g., white-blood-cell count or hemoglobin A1c) within the EHR but would also allow visualization of flow-volume loops and indicators of testing quality (e.g., acceptable and reproducible spirometric effort).

We hope that today's Implementation Guide release acts as a collaborative catalyst for future development. To that end, we are seeking research collaborators to advance this project beyond its current draft state, and to advance the interoperability agenda for pulmonary function data (say hi 👋 to founders@automatemedical.com)

Special thanks to everyone who ever took a call with us about pulmonary function tests and to Joe Conroy (@jamais-vu) for dev assistance.

FAQs

What is an Implementation Guide?

A FHIR Implementation Guide or IG is a bundle of rules on how to solve a specific health data standards problem. The IG is used to gather all of the parts and systems necessary to describe a solution to the problem.

What is FHIR?

FHIR is a health data standard of the future, and increasingly the present.

What is the status of this guide? Who is using it?

This is the very first published build of this IG (0.1.0). We have labelled it appropriately as a draft. We are seeking clinical collaborators for input.

We are using it internally on our PFT Extractor project to format export results.

How can I collaborate with you on this IG?

If you are an interested clinician, researcher, hardware device manufacturer, or other systems vendor in the pulmonary function space we would love to work with you collaboratively. We can be reached directly at founders@automatemedical.com.

This Implementation Guide an open source project and is Apache 2.0 licensed. Contributions can be openly made directly to automate-medical/pft-ig.

I have a similar sounding health data problem, can you help?

Working with health data is hard. We build open source dev tools for health data standards like FHIR with modern languages and frameworks and produce projects like this new implementation guide. We'd love to hear about your health data problem at founders@automatemedical.com.